Show HN: 188M Hindi encoder, 28B tokens, 8K context, 1× RTX 4090
Description and use
A 188 M Hindi encoder trained on 28 B tokens with an 8 K context window, using a single RTX 4090. It can be adopted for NLP prototypes by loading it via Hugging Face and validating compatibility with your data. The project is prototype‑grade: manual vetting of dependencies, license, and update cadence is needed before production use.
Use in a workflow
Show HN: 188M Hindi encoder, 28B tokens, 8K context, 1× RTX 4090 may be useful when its README and activity match a concrete workflow.
Limitations and review notes
Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.
- Source: hackernews
- Record date: 2026-09-06T14:57:35.000Z